Fair Embedding Engine: A Library for Analyzing and Mitigating Gender Bias in Word Embeddings

TL;DR

The paper introduces Fair Embedding Engine, a library designed to analyze and reduce gender bias in word embeddings, facilitating easier evaluation and development of debiasing techniques.

Contribution

It presents a comprehensive library that combines state-of-the-art methods for quantifying, visualizing, and mitigating gender bias in word embeddings.

Findings

FEE enables fast analysis of bias in embeddings.

It supports rapid prototyping of debiasing methods.

The library maintains embedding utility while reducing bias.

Abstract

Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these biases while keeping the syntactic and semantic utility of embeddings intact. This paper describes Fair Embedding Engine (FEE), a library for analysing and mitigating gender bias in word embeddings. FEE combines various state of the art techniques for quantifying, visualising and mitigating gender bias in word embeddings under a standard abstraction. FEE will aid practitioners in fast track analysis of existing debiasing methods on their embedding models. Further, it will allow rapid prototyping of new methods by evaluating their performance on a suite of standard metrics.